IdentityLink<T>
Models & Types · AiDotNet.LinkFunctions
Identity link function: g(μ) = μ.
Implements: ILinkFunction<T>
For Beginners
Use this for standard linear regression where predictions can be any real number. There’s no transformation - what you predict is what you get.
How It Works
The identity link is the canonical link for the Normal (Gaussian) distribution. It makes no transformation, so the linear predictor equals the mean directly.
Constructors
| Constructor | Summary |
|---|---|
IdentityLink() |
Properties
| Property | Summary |
|---|---|
bool IsCanonical { get; } |
|
string Name { get; } |
Methods
| Method | Summary |
|---|---|
T InverseLink(T eta) |
|
T InverseLinkDerivative(T eta) |
|
T Link(T mu) |
|
T LinkDerivative(T mu) |
|
T Variance(T mu) |